In [1]:
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import plotly.express as px
import plotly.io as pio
In [2]:
hike_df = pd.read_csv('hike_data.csv')
speed_df = pd.read_csv('speed_data.csv')
In [3]:
hike_df.head()
Out[3]:
Latitude Longitude Elevation
0 51.20257 -115.59737 1691.0
1 51.20259 -115.59734 1691.0
2 51.20262 -115.59732 1692.0
3 51.20265 -115.59730 1692.0
4 51.20268 -115.59729 1693.0
In [4]:
speed_df.head()
Out[4]:
kilometers avg_speed elevation_gain
0 1 4.82 37 m
1 2 5.10 58 m
2 3 4.89 18 m
3 4 4.75 103 m
4 5 4.06 157 m
In [5]:
hike_df.dtypes
Out[5]:
Latitude     float64
Longitude    float64
Elevation    float64
dtype: object
In [6]:
speed_df.dtypes
Out[6]:
kilometers          int64
avg_speed         float64
elevation_gain     object
dtype: object
In [7]:
speed_df['elevation_gain'] = speed_df['elevation_gain'].str.rstrip(' m').astype(float)
In [8]:
speed_df.head()
Out[8]:
kilometers avg_speed elevation_gain
0 1 4.82 37.0
1 2 5.10 58.0
2 3 4.89 18.0
3 4 4.75 103.0
4 5 4.06 157.0
In [9]:
speed_df.dtypes
Out[9]:
kilometers          int64
avg_speed         float64
elevation_gain    float64
dtype: object
In [10]:
hike_df.isna().sum()
Out[10]:
Latitude     0
Longitude    0
Elevation    0
dtype: int64
In [11]:
speed_df.isna().sum()
Out[11]:
kilometers        0
avg_speed         0
elevation_gain    0
dtype: int64
In [12]:
hike_df.describe()
Out[12]:
Latitude Longitude Elevation
count 5023.000000 5023.000000 5023.000000
mean 51.224317 -115.598374 1959.351185
std 0.008697 0.012297 362.045170
min 51.202570 -115.612320 1566.000000
25% 51.219150 -115.608430 1643.000000
50% 51.226040 -115.602320 1813.000000
75% 51.231445 -115.590180 2264.000000
max 51.236140 -115.569570 2737.000000
In [13]:
speed_df.describe()
Out[13]:
kilometers avg_speed elevation_gain
count 19.000000 19.000000 19.000000
mean 10.000000 4.650000 79.157895
std 5.627314 2.040319 77.053562
min 1.000000 1.480000 0.000000
25% 5.500000 3.280000 2.000000
50% 10.000000 4.820000 58.000000
75% 14.500000 5.165000 153.500000
max 19.000000 9.050000 208.000000
In [14]:
distance = 19.05
num_row = len(hike_df) - 1
distance_per_row = distance/num_row
In [15]:
hike_df['Distance'] = hike_df.index * distance_per_row
In [16]:
hike_df
Out[16]:
Latitude Longitude Elevation Distance
0 51.20257 -115.59737 1691.0 0.000000
1 51.20259 -115.59734 1691.0 0.003793
2 51.20262 -115.59732 1692.0 0.007587
3 51.20265 -115.59730 1692.0 0.011380
4 51.20268 -115.59729 1693.0 0.015173
... ... ... ... ...
5018 51.20312 -115.59774 1689.0 19.034827
5019 51.20309 -115.59772 1689.0 19.038620
5020 51.20307 -115.59768 1690.0 19.042413
5021 51.20304 -115.59765 1690.0 19.046207
5022 51.20299 -115.59759 1691.0 19.050000

5023 rows × 4 columns

In [17]:
check = hike_df[hike_df['Elevation'] == 2737]
check
Out[17]:
Latitude Longitude Elevation Distance
2733 51.22513 -115.56963 2737.0 10.367115
In [18]:
fig, ax = plt.subplots(1,1,figsize=(8,6))

ax.plot(hike_df['Distance'], hike_df['Elevation'])
ax.set_title("Cascade Mountain (2998 meters): Hiking Elevation Gain")
ax.set_ylabel("Elevation (meters)")
ax.set_xlabel("Distance (km)")

plt.savefig("LineChart-Cascade.png")
plt.show()
In [19]:
fig, ax = plt.subplots(1,1,figsize=(8,6))

scatter = ax.scatter(hike_df['Longitude'], hike_df['Latitude'], c=hike_df['Elevation'], cmap='plasma')
plt.colorbar(scatter, label='Elevation (meters)')

ax.set_xlabel('Longitude')
ax.set_ylabel('Latitude')
ax.set_title("Longitude, Latitdue Scatterplot w/ Elevation Colorbar")
plt.savefig("2dScatterplot-Cascade1.png")
plt.show()
In [20]:
fig = px.scatter_mapbox(hike_df, lat='Latitude', lon='Longitude',
                       width=850, zoom=12, mapbox_style='open-street-map')
plt.savefig("2dScatter-Cascade.png")
fig.show()

<Figure size 640x480 with 0 Axes>
In [21]:
fig = px.scatter_3d(hike_df, x='Longitude', y='Latitude', z='Elevation', color='Elevation')

fig.update_layout(
    title='Latitude, Longitude, and Elevation: Cascade Mountain',
    autosize=False,
    width=1000,  
    height=800,  
)

pio.write_html(fig, "3dScatterplot-Cascade.html")
fig.show()
In [22]:
rows_per_km = np.round(num_row/distance).astype(int)
rows_per_km
Out[22]:
264
In [23]:
def calculate_elevation_change(row1, row2, df):
    return df.at[row2, 'Elevation'] - df.at[row1, 'Elevation']

intervals = range(0, num_row, rows_per_km)

elevation_change = []

for i in range(len(intervals) - 1):
    start_row = intervals[i]
    end_row = intervals[i + 1]
    change = calculate_elevation_change(start_row, end_row, hike_df)
    elevation_change.append(change)
    
speed_df['elevation_change'] = elevation_change

speed_df
Out[23]:
kilometers avg_speed elevation_gain elevation_change
0 1 4.82 37.0 -50.0
1 2 5.10 58.0 -10.0
2 3 4.89 18.0 -64.0
3 4 4.75 103.0 99.0
4 5 4.06 157.0 138.0
5 6 3.45 150.0 162.0
6 7 3.69 163.0 157.0
7 8 2.27 189.0 182.0
8 9 2.01 208.0 200.0
9 10 1.48 202.0 168.0
10 11 2.81 3.0 -79.0
11 12 3.11 0.0 -208.0
12 13 6.11 0.0 -259.0
13 14 7.51 0.0 -219.0
14 15 9.05 1.0 -170.0
15 16 8.31 0.0 -156.0
16 17 4.86 84.0 49.0
17 18 5.23 42.0 14.0
18 19 4.84 89.0 44.0
In [24]:
bar_width = 0.2

positions = range(len(speed_df['kilometers']))

fig, ax = plt.subplots(figsize=(10,8))

ax.bar([pos - bar_width for pos in positions], speed_df['elevation_change'], width=bar_width, label='Elevation Change (m)', color='orange')

ax2 = ax.twinx()

ax2.bar(positions, speed_df['avg_speed'], width=bar_width, label='Average Speed (km/h)')

ax.set_ylabel('Elevation Change per KM (meters)')
ax.set_ylim(min(speed_df['elevation_change'] * 1.2), max(speed_df['elevation_change']) * 1.2)

ax2.set_ylabel('Average Speed per KM (km/h)')
ax2.set_ylim(min(speed_df['elevation_change'] * 0.1), max(speed_df['elevation_change']) * 0.1)

ax.set_xticks(positions)
ax.set_xticklabels(speed_df['kilometers'].astype(str))
ax.set_xlabel("Distance in Kilometers")

lines, labels = ax.get_legend_handles_labels()
lines2, labels2 = ax2.get_legend_handles_labels()

ax.legend(lines + lines2, labels + labels2, loc='upper right')
plt.title('Elevation Change and Average Speed for each Kilometer (Cascade Hike analysis)')
plt.savefig("ElevationSpeed-Cascade.png")
plt.show()